Update app.py

app.py

@@ -1,3 +1,11 @@
+# ============================================
+# RAGify Bilal - Optimized RAG Chatbot
+# ============================================
+
+# 1. Install dependencies (Colab only, skip in Hugging Face Spaces)
+!pip install faiss-cpu gradio groq pypdf sentence-transformers
+
+# 2. Imports
 import os
 import faiss
 import gradio as gr
@@ -5,31 +13,27 @@ from groq import Groq
 from sentence_transformers import SentenceTransformer
 from pypdf import PdfReader
 
-# Use Hugging Face secret for API key
+# 3. Setup Groq API key (replace with your key or set via Hugging Face Secrets)
+os.environ["GROQ_API_KEY"] = "YOUR_GROQ_API_KEY"
 client = Groq(api_key=os.environ["GROQ_API_KEY"])
 
-# Embedding model
+# 4. Load embedding model
 embedder = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
 
-# Global FAISS index and chunks
+# 5. Globals
 index = None
 chunks = []
 chat_history = []
 
-# Chunking with overlap
+# 6. Chunking with overlap
 def chunk_text(text, chunk_size=200, overlap=50):
     words = text.split()
-    chunks = []
-    for i in range(0, len(words), chunk_size - overlap):
-        chunk = " ".join(words[i:i+chunk_size])
-        chunks.append(chunk)
-    return chunks
+    return [" ".join(words[i:i+chunk_size]) for i in range(0, len(words), chunk_size - overlap)]
 
-# Load and process uploaded files
+# 7. Process uploaded files
 def process_files(files):
     global index, chunks
     chunks = []
-
     try:
         for file in files:
             if file.name.endswith(".pdf"):
@@ -46,7 +50,6 @@ def process_files(files):
         if not chunks:
             return "⚠️ No text found in uploaded files."
 
-        # Create embeddings
         embeddings = embedder.encode(chunks)
         dimension = embeddings.shape[1]
         index = faiss.IndexFlatL2(dimension)
@@ -56,7 +59,7 @@ def process_files(files):
     except Exception as e:
         return f"❌ Error processing files: {str(e)}"
 
-# Retriever
+# 8. Retriever
 def retrieve(query, k=3):
     if index is None:
         return ["⚠️ No files uploaded yet."]
@@ -64,7 +67,7 @@ def retrieve(query, k=3):
     D, I = index.search(q_emb, k)
     return [chunks[i] for i in I[0]]
 
-# RAG pipeline with chat history
+# 9. RAG pipeline
 def rag_pipeline(query, model_choice):
     retrieved = retrieve(query)
     context = "\n".join(retrieved)
@@ -80,18 +83,12 @@ def rag_pipeline(query, model_choice):
     except Exception as e:
         return f"❌ Error generating answer: {str(e)}", chat_history
 
-# Gradio UI
+# 10. Gradio UI
 with gr.Blocks() as demo:
-    gr.Markdown(
-        """
-        # 🌟 ContextPilot Bilal
-        ### Upload multiple documents and ask optimized questions
-        ---
-        """
-    )
+    gr.Markdown("# 🌟 ContextPilot Bilal\n### Upload documents and ask optimized questions")
 
     with gr.Tab("Upload Files"):
-        file_input = gr.File(label="📂 Upload PDF or Text Files", file_types=[".pdf", ".txt"], type="file", file_types_multiple=True)
+        file_input = gr.File(label="📂 Upload PDF or Text Files", file_types=[".pdf", ".txt"], type="file", file_types="multiple")
         process_btn = gr.Button("🚀 Process Files")
         status_output = gr.Textbox(label="Status", interactive=False)
         process_btn.click(process_files, inputs=file_input, outputs=status_output)
@@ -109,5 +106,5 @@ with gr.Blocks() as demo:
 
         ask_btn.click(rag_pipeline, inputs=[query_input, model_choice], outputs=[answer_output, history_output])
 
-# ✅ Pass theme in launch (Gradio 6.0 change)
+# ✅ Theme must be passed in launch
 demo.launch(theme=gr.themes.Soft(primary_hue="blue", secondary_hue="violet"))